v2 CN: real-data validation vs NYGC 30x SVs (interim), noise gate on normalised LRR (K-027)

GSE165845 360 arrays: constitutional DEL/DUP calls 77/74 % in the NYGC SV truth, LOH reproduced across replicates 74 %; mosaic calls are mostly false positives (12-23 %), sensitivity for 25 kb-1 Mb events 7-13 % at QUAL >= 20. All samples had been flagged SampleQuality by the summary logr_dev (cluster-file mismatch); the gate now uses the SD of the LRR after the batch reference. Validation script: --ignore-filter. Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
2026-09-29 07:42:06 +01:00
1 parent 65502eb8e4
commit 07a4caff51
@@ -0,0 +1,89 @@
+{
+ "samples": 360,
+ "min_qual": 20.0,
+ "ignored_filters": [
+  "SampleQuality"
+ ],
+ "sensitivity": {
+  "DEL": {
+   "100-500kb": {
+    "found": 126,
+    "truth": 1554,
+    "rate": 0.0811
+   },
+   "1000-infkb": {
+    "found": 0,
+    "truth": 15,
+    "rate": 0.0
+   },
+   "25-50kb": {
+    "found": 16,
+    "truth": 225,
+    "rate": 0.0711
+   },
+   "50-100kb": {
+    "found": 70,
+    "truth": 894,
+    "rate": 0.0783
+   },
+   "500-1000kb": {
+    "found": 13,
+    "truth": 180,
+    "rate": 0.0722
+   }
+  },
+  "DUP": {
+   "100-500kb": {
+    "found": 117,
+    "truth": 1059,
+    "rate": 0.1105
+   },
+   "1000-infkb": {
+    "found": 6,
+    "truth": 21,
+    "rate": 0.2857
+   },
+   "25-50kb": {
+    "found": 1,
+    "truth": 198,
+    "rate": 0.0051
+   },
+   "50-100kb": {
+    "found": 15,
+    "truth": 462,
+    "rate": 0.0325
+   },
+   "500-1000kb": {
+    "found": 10,
+    "truth": 78,
+    "rate": 0.1282
+   }
+  }
+ },
+ "precision": {
+  "DEL": {
+   "in_truth": 222,
+   "calls": 571,
+   "rate": 0.3888
+  },
+  "DUP": {
+   "in_truth": 149,
+   "calls": 436,
+   "rate": 0.3417
+  }
+ },
+ "replicate_reproducibility": {
+  "CNV": {
+   "matched": 554,
+   "comparisons": 2014,
+   "rate": 0.2751
+  },
+  "LOH": {
+   "matched": 286,
+   "comparisons": 394,
+   "rate": 0.7259
+  }
+ },
+ "calls_per_sample_median": 2.0,
+ "loh_calls_per_sample_median": 0.0
+}